Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
YoanWaiSkillYoanWai/agent-manager/skills/agent-manager-reference/SKILL.md
Query agent-manager.dev's reference API and MCP server for documentation, the coding CLIs it manages, the tools its MCP server exposes, and the current release. Use instead of scraping the website's HTML.
skillberry-aiSkillskillberry-ai/cap-evolve/skills/capabilities/mcp-tool/SKILL.md
Optimize the tool surface of an EXTERNAL MCP server — one the agent talks to but does not implement. Use when an agent wired to an MCP server mis-selects tools, fills arguments wrong, or is offered a noisy 40-tool set it mostly ignores. Covers MCP tool descriptions, per-parameter documentation, in-description examples, and curating which of the server's tools are exposed to the model. Only those documentation-level edits are safe here: the server owns the wire inputSchema and the handler code, so an edit that changes either produces a candidate that breaks against the real server. Use the `tools` capability instead when the agent owns its tool code and schema. The two differ only by who owns the tool implementation; the deciding question is who owns the artifact being edited, so an agent-owned wrapper around an MCP server is `tools` for the wrapper's own code and `mcp-tool` for the upstream tool defs.
addiplusSkilladdiplus/mcp-builder/SKILL.md
Build production MCP servers with dual transport (stdio + HTTP) and OAuth 2.1 for Claude Co-Work. Covers server design, tool definitions, Vercel deployment, and the full OAuth ceremony. Use when building a new MCP server, adding HTTP transport, adding OAuth, or deploying to Vercel. Triggers on "MCP server", "build MCP", "create MCP", "Co-Work", "mcp-builder", "remote MCP".
patonkikhSkillpatonkikh/APES/skills/mcp/mcp-security-review/skill.md
Conduct a security review of MCP server and client implementations: threat modeling, auth validation, tool risk assessment, and remediation plan aligned with OWASP LLM and MCP-specific risks. Use when working on MCP servers, MCP tools, MCP clients, or Model Context Protocol integrations.
gotempshSkillgotempsh/temps/skills/temps-mcp-setup/SKILL.md
Configure Temps as an MCP (Model Context Protocol) server so AI assistants can interact with a Temps instance directly -- listing/inspecting projects and deployments, and (when write mode is enabled) triggering deployments with human confirmation. Use when the user wants to: (1) Set up the Temps MCP server, (2) Connect Claude Code/Desktop, Codex, Cursor, VS Code, Windsurf, or Zed to Temps, (3) Add Temps tools to an AI assistant, (4) Test the MCP wizard locally, (5) Manage multiple Temps MCP connections (dev, staging, prod, or several local dev slots) side by side. Triggers: "temps mcp", "configure temps tools", "add temps to claude", "temps ai assistant", "mcp server setup", "mcp add", "test the mcp wizard".
cdgutierrez6Skillcdgutierrez6/claude-skills/skills/mcp-engineer/SKILL.md
Actúa como MCP Engineer Senior especializado en Model Context Protocol. Úsalo para: diseñar e implementar MCP servers (TypeScript SDK, Python SDK), definir tools/resources/ prompts como primitivas MCP, configurar transports (stdio, SSE, HTTP Streamable), integrar MCP servers en Claude Code / Claude Desktop / Claude API, crear workflows de automatización via MCP, auditar seguridad de MCP servers, y conectar ecosistemas heterogéneos (bases de datos, APIs externas, sistemas legacy) como contexto para LLMs. Actívalo con: "crea un MCP server", "quiero que Claude pueda acceder a", "implementa la tool MCP para", "diseña el MCP para mi CRM", "integra [sistema] via MCP", "Claude no puede acceder a mis datos", o cualquier tarea de integración de contexto externo con modelos de lenguaje mediante el protocolo MCP.
MicrosoftSkillmicrosoft/Building-AI-Agents-From-Zero-To-Production/.github/skills/mcp-integration/SKILL.md
Help a learner give an agent tools through the Model Context Protocol (MCP) — both client-side MCP and Foundry Hosted MCP tools. Use when connecting an agent to an MCP server (e.g. the GitHub MCP server), adding a remote tool, or reasoning about MCP approval/governance.
punitaraniSkillpunitarani/fli/skills/fli/SKILL.md
Guidance for installing and using Fli correctly as a CLI and MCP server. Use when: setting up Fli with pipx, running `fli` flight searches, configuring Claude Desktop with `fli-mcp`, using the HTTP MCP server, or troubleshooting Fli command availability and common usage mistakes.
agentcloakSkillagentcloak/skill/skills/agentcloak/SKILL.md
Use this skill when managing InCountry AgentCloak — editing environment configurations via Portal API export/import, and interacting with the MCP cloaking/uncloaking server. Covers the three-layer architecture: Portal API (REST at portal.incountry.com/api), MCP Server (JSON-RPC 2.0 at dynamic mcp_server_url), and external services proxied through the MCP layer.
malkreideSkillmalkreide/mcp-audit-skill/skills/mcp-data-source-probe/SKILL.md
Standardisiertes 3-Schritte-Vorgehen zur Evaluation, Architektur-Entscheidung und Implementation von `*-mcp`-Servern im Swiss Public Data MCP Portfolio. Verwende diesen Skill IMMER wenn der User (1) einen neuen MCP-Server plant oder baut, (2) eine neue Datenquelle für einen bestehenden Server evaluiert, (3) einen Server um zusätzliche Tools erweitern will, (4) fragt ob eine bestimmte API/Datenquelle geeignet ist, (5) einen bestehenden MCP-Server refaktoriert, (6) Begriffe wie «MCP-Server», «neue Datenquelle anbinden», «API prüfen», «Live-Probe», «Datenquelle evaluieren», «welche Tools», «kann ich das nutzen» erwähnt, (7) für einen `*-mcp`-Server einen Scaffold anfordert, oder (8) meldet, dass ein Server zu wenige oder keine Treffer liefert, obwohl die Daten in der Quelle vorhanden sind («findet nichts», «zu wenig Resultate», «Web-UI zeigt mehr», «leeres Ergebnis», «Recall», «Scope»). Auch bei allgemeinen Aussagen wie «ich würde gerne X via MCP anbinden» oder «gibt es Daten von Y» diesen Skill anwenden.
PostHogSkillPostHog/posthog/.agents/skills/debugging-mcp-analytics/SKILL.md
Debug, support, and build PostHog MCP Analytics — product analytics for MCP servers (the `@posthog/mcp` and `posthog.mcp` SDKs plus the mcp_analytics product). Use when MCP analytics data looks wrong or missing ("events aren't showing", "intent clusters are empty", "sessions are missing", "per-tool numbers look wrong"), when writing queries over `$mcp_*` events by hand, or when doing feature work on the SDKs, the dashboard and its query runners, the self-instrumented MCP server, the `wizard mcp-analytics` install command, or the in-app onboarding. Covers the repo map, the `$mcp_*` vocabulary and where each property comes from, the rules that silently corrupt metrics when ignored, the end-to-end pipeline and where each stage breaks, and which repo to change. For reading the data rather than fixing it, prefer the `exploring-mcp-*` and `improving-mcp-tools` skills.
usetrmnlSkillusetrmnl/trmnl-agent-skills/skills/trmnl/SKILL.md
Use when working on anything TRMNL — building plugins, writing or editing markup, designing layouts using the TRMNL CSS framework, calling the TRMNL MCP server (mcp__trmnl__*), or any task that mentions "trmnl", "e-ink display", "trmnl.com", "TRMNL plugin", "Liquid markup", "image-dither", "title_bar", or screen sizes 800x480 / 800x240 / 400x480 / 400x240. References embed the production prompts TRMNL's external MCP server ships — agent rules, the full design system template guide, and the framework v3 supplement.
darellchua2Skilldarellchua2/civiltekk-opencode-claude-skills/skills/mcp-install-assistant-skill/SKILL.md
Interactive MCP installation assistant — inventories shipped MCP servers and provider packs from the deployed config, prechecks prerequisites (env keys, node, Chrome, pip), enables globally via --enable-pack or per-project v2 config, verifies with opencode mcp list. Triggers: install mcp, enable mcp, which mcp, set up mcp server, mcp assistant.
arcee-aiSkillarcee-ai/nac/skills/nac-onboarding/SKILL.md
Install and configure Arcee AI nac, get the user into the nac dashboard, and connect their MCP client to nac. Use when a user asks to get started with nac, connect nac to an agent, add MCP servers, or expose nac's MCP server to Claude Code, Codex, OpenCode, or another MCP client.
like-a-freedomSkilllike-a-freedom/rusty_apple_mail_mcp/.agents/skills/mcp-design/SKILL.md
Design intent-driven MCP servers — use when creating, reviewing, or refactoring an MCP server or its tools.
MongoDBSkillmongodb/docs/.claude/skills/mcp-release-notes/SKILL.md
Draft MongoDB MCP Server release notes for a new version by fetching the corresponding release from mongodb-js/mongodb-mcp-server and formatting them for the docs. Use when asked to draft or create MCP Server release notes.
TheDecipheristSkillTheDecipherist/claude-code-mastery-project-starter-kit/.claude/skills/mcp-builder/SKILL.md
Build a high-quality MCP server that exposes a service or API to an LLM through well-designed tools. Use when asked to create, scaffold, or add an MCP server, wrap an API as MCP tools, or expose a service to Claude/agents. Writes files, so it runs only when invoked explicitly.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.
